© 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. 102661
    Prev
    Next
    INDEX
    Explanations

    common word sequences

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

    sacrificing new lives

    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
    ون
    0.54
    on
    0.53
    ي
    0.52
    it
    0.49
    users
    0.49
    ot
    0.47
    ان
    0.47
    off
    0.47
    i
    0.46
    뢰
    0.45
    POSITIVE LOGITS
    уро
    0.46
    竣工
    0.45
    obal
    0.45
    回来
    0.42
     तुर
    0.41
     lluv
    0.41
     श्रद्धांजलि
    0.40
     vali
    0.40
     breezy
    0.40
     NGS
    0.40
    Activations Density 0.001%

    No Known Activations