© 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. 126139
    Prev
    Next
    INDEX
    Explanations

    available as, the sun, publication of

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

    documentary, human, provides

    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
    Johnny
    0.46
    ってます
    0.44
     далі
    0.43
    ቦች
    0.43
    NOT
    0.43
    ビア
    0.43
    진
    0.43
    хів
    0.43
    Uma
    0.42
    ิด
    0.42
    POSITIVE LOGITS
    taught
    0.47
     conna
    0.45
     enlighten
    0.45
    r
    0.43
     moulds
    0.43
    iapkan
    0.43
     poder
    0.42
    或者是
    0.42
     autón
    0.42
     countenance
    0.42
    Activations Density 0.000%

    No Known Activations