© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22000
    Prev
    Next
    INDEX
    Explanations

    words are followed by specific continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     中的
    0.44
     മൊ
    0.44
     Kindle
    0.44
    Money
    0.42
    獷
    0.41
    റുക
    0.40
     Léon
    0.40
     vele
    0.39
     gü
    0.39
     falsch
    0.39
    POSITIVE LOGITS
    s
    0.62
    ла
    0.52
     affords
    0.49
    pea
    0.47
     streamed
    0.46
    esercizio
    0.46
     bezpiecze
    0.45
     admittedly
    0.45
    iritto
    0.45
     recessed
    0.45
    Activations Density 0.002%

    No Known Activations