© 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. 83117
    Prev
    Next
    INDEX
    Explanations

    descriptive words and instructions

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

    year old

    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
     behandling
    0.45
     मुस्लिम
    0.45
     অসাধারণ
    0.44
    𝕒
    0.44
     शानदार
    0.43
     Continue
    0.43
    แนะนำ
    0.42
     Become
    0.42
     Becoming
    0.42
    警察
    0.42
    POSITIVE LOGITS
    muster
    0.47
     itt
    0.45
    шого
    0.44
    بري
    0.44
     cohé
    0.43
     alluvial
    0.43
     unobstructed
    0.43
    phalodes
    0.42
    尃
    0.41
    cnty
    0.40
    Activations Density 0.000%

    No Known Activations