© 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. 51877
    Prev
    Next
    INDEX
    Explanations

    eternal faithfulness

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

    equipment, ritual, sense, or data

    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
    .!
    0.44
    .³
    0.43
    <unused178>
    0.43
    <unused451>
    0.43
    第七
    0.42
    <unused692>
    0.42
     renamed
    0.42
     теперь
    0.41
     వల్ల
    0.41
    ¾
    0.41
    POSITIVE LOGITS
    們
    0.46
    Props
    0.44
     composants
    0.43
     kami
    0.42
     Bete
    0.41
    Cookies
    0.40
    参与
    0.40
     μας
    0.39
     similaires
    0.39
     ItemStack
    0.39
    Activations Density 0.000%

    No Known Activations