© 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. 51698
    Prev
    Next
    INDEX
    Explanations

    weather outside descriptions

    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
    StartAddress
    0.52
    扉
    0.48
    ॉल
    0.45
    ıldığı
    0.45
    >(</
    0.44
     annoyed
    0.44
     offended
    0.44
     genitori
    0.43
     shoving
    0.43
    当作
    0.42
    POSITIVE LOGITS
    </h2>
    0.61
    idad
    0.58
    ъ
    0.54
    idade
    0.53
    quer
    0.51
    serie
    0.51
     Franchise
    0.51
     CRF
    0.50
     Pag
    0.48
    authent
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.