© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98188
    Prev
    Next
    INDEX
    Explanations

    terms would, add water, optical specification, elements at, questions that, but I, doggie gie, schedule ( , expressed in

    np_acts-logits-general · gemini-2.5-flash-lite

    problem questions correctly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cre
    0.46
    罗斯
    0.44
    Finance
    0.44
    id
    0.42
    +}$
    0.42
    Flex
    0.42
    Credentials
    0.41
    ﺯ
    0.41
    兼
    0.41
    Wallet
    0.40
    POSITIVE LOGITS
     কোষ
    0.52
     allgeme
    0.51
     Panch
    0.50
     kiedy
    0.50
     umjet
    0.49
     prefque
    0.48
     esfera
    0.47
     experto
    0.46
     suddiv
    0.46
    அது
    0.45
    Activations Density 0.001%

    No Known Activations