© 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. 74997
    Prev
    Next
    INDEX
    Explanations

    understanding adaptation and quick checks

    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
    un
    0.50
    ang
    0.49
    ab
    0.47
    ug
    0.46
    og
    0.44
     lua
    0.44
    か
    0.43
     Determin
    0.43
    üglich
    0.43
    Max
    0.42
    POSITIVE LOGITS
    hamento
    0.47
    榭
    0.47
    PARATOR
    0.46
    peuta
    0.44
    これを
    0.43
    sprach
    0.43
     Produkten
    0.43
    𝙫
    0.42
    ប្ប
    0.42
     produkt
    0.41
    Activations Density 0.001%

    No Known Activations