© 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. 224792
    Prev
    Next
    INDEX
    Explanations

    weekly frequency

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

    lists of terms and following words

    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
     lettres
    0.51
    getLogger
    0.51
    ítés
    0.50
     cittam
    0.49
     anglais
    0.49
     ligaments
    0.49
     appartenant
    0.49
    靳
    0.49
     abhid
    0.48
    ôts
    0.48
    POSITIVE LOGITS
     “
    0.46
    ikaze
    0.44
    entre
    0.43
     Phoenix
    0.43
     Aggregate
    0.43
    nova
    0.42
    ANCED
    0.42
    truck
    0.42
    decimal
    0.41
    apit
    0.41
    Activations Density 0.000%

    No Known Activations