© 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. 125514
    Prev
    Next
    INDEX
    Explanations

    condition. discussing sleeping. debt counselor. not commit. vehicle maintenance

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

    This followed by is

    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
    tan
    0.48
    tern
    0.46
     splinter
    0.45
    .
    0.44
    t
    0.44
    ►
    0.43
    got
    0.43
    kot
    0.43
     inhe
    0.43
     appearances
    0.42
    POSITIVE LOGITS
     同じ
    0.51
     少し
    0.50
     പറയാ
    0.49
     ሌ
    0.48
     けれど
    0.48
     還
    0.47
     ኦ
    0.47
     الحاله
    0.46
     イ
    0.46
     có
    0.46
    Activations Density 0.000%

    No Known Activations