© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 180905
    Prev
    Next
    INDEX
    Explanations

    care, system, then

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

    languages, speak, voice, functions, shipping, updated

    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
    אָ
    0.52
     இணைப்பு
    0.49
    reat
    0.48
    razione
    0.47
    ריה
    0.46
    essen
    0.46
    Naz
    0.46
    Ű
    0.46
    يمة
    0.46
    wirkung
    0.46
    POSITIVE LOGITS
     this
    0.68
     would
    0.59
     chassis
    0.55
     may
    0.54
     scenario
    0.54
     juj
    0.54
     swabs
    0.53
     should
    0.53
     seals
    0.53
     loyal
    0.52
    Activations Density 0.002%

    No Known Activations