© 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. 25938
    Prev
    Next
    INDEX
    Explanations

    prints on, findings of, different study

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

    threat model

    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
    -
    0.48
    ,
    0.47
     g
    0.44
    Resolve
    0.44
    /
    0.42
     p
    0.42
     detect
    0.42
     ze
    0.41
    .
    0.41
     kund
    0.41
    POSITIVE LOGITS
     ओवरटाइम
    0.52
    ﺽ
    0.52
    মনির
    0.51
    चार्ज
    0.50
    椏
    0.50
     doigt
    0.48
     IndexError
    0.46
    ୍ୟ
    0.46
     AppMethodBeat
    0.46
     embroidered
    0.46
    Activations Density 0.000%

    No Known Activations