© 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. 237886
    Prev
    Next
    INDEX
    Explanations

    resulting in

    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
    пи
    0.45
    ╬
    0.42
    fills
    0.42
    recorded
    0.42
    inserted
    0.42
    ф
    0.42
    يها
    0.41
    inescent
    0.41
    訳
    0.40
    fi
    0.40
    POSITIVE LOGITS
     inden
    0.43
     austen
    0.43
     ans
    0.43
     distanc
    0.42
     ጣ
    0.42
     silenc
    0.42
     Nationals
    0.42
     dificult
    0.41
     altid
    0.41
     frio
    0.41
    Activations Density 0.001%

    No Known Activations