© 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. 177580
    Prev
    Next
    INDEX
    Explanations

    religious or descriptive terms

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

    Llama 2 (previously Llama 1)

    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
     freelancer
    0.52
    \%$
    0.46
     negocios
    0.46
     checkIf
    0.46
    lastCursor
    0.46
    釀
    0.45
     performer
    0.45
     counsellor
    0.45
     منسل
    0.45
    囩
    0.45
    POSITIVE LOGITS
    it
    0.58
     простран
    0.52
    ar
    0.52
    rq
    0.49
    ag
    0.47
    sheet
    0.46
    tes
    0.46
    rj
    0.46
     чаще
    0.45
    ты
    0.45
    Activations Density 0.001%

    No Known Activations