© 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. 202509
    Prev
    Next
    INDEX
    Explanations

    phrases starting with common verbs or nouns

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

    early EV

    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
    </h6>
    0.47
    Hospital
    0.46
    Booth
    0.44
    ⚫
    0.43
    Failure
    0.43
    MenuStrip
    0.43
    র্
    0.42
    ="
    0.41
    Failed
    0.41
     pover
    0.41
    POSITIVE LOGITS
    ޔ
    0.46
    itionally
    0.43
     అలాంటి
    0.42
    というと
    0.41
     전환
    0.39
    aminan
    0.39
     نہ
    0.39
     технологий
    0.39
     미국의
    0.39
     एंट्री
    0.38
    Activations Density 0.000%

    No Known Activations