© 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. 206627
    Prev
    Next
    INDEX
    Explanations

    seriously for emphasis

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

    things made or derived

    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
    ඓ
    0.48
     deserts
    0.46
     timestamps
    0.46
     references
    0.45
     wilderness
    0.44
     codons
    0.44
     studs
    0.43
    зир
    0.43
     Arctic
    0.41
    మన్
    0.41
    POSITIVE LOGITS
    ccion
    0.55
     כ
    0.54
     funcionamiento
    0.54
    ignement
    0.53
     NÃO
    0.53
     производ
    0.51
     obtenido
    0.51
     parámetro
    0.51
    queen
    0.50
     Lle
    0.49
    Activations Density 0.002%

    No Known Activations