© 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. 124170
    Prev
    Next
    INDEX
    Explanations

    keys / locks

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

    abstract concepts or non-english

    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
    accompagn
    0.57
    ͯ
    0.57
     подро
    0.55
     microtub
    0.55
     adulte
    0.55
    trx
    0.53
     esport
    0.53
     фізи
    0.52
     apparten
    0.51
     déprimées
    0.51
    POSITIVE LOGITS
    يان
    0.49
    稱
    0.45
    ാത്ത
    0.45
     keys
    0.42
    匙
    0.41
    ละ
    0.40
    amas
    0.40
    나
    0.40
    ْت
    0.40
     Schlüssel
    0.39
    Activations Density 0.000%

    No Known Activations