© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82939
    Prev
    Next
    INDEX
    Explanations

    requires instructions or details

    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
    pak
    0.46
    <0x0D>
    0.45
    beta
    0.45
    YY
    0.45
    vas
    0.45
    trä
    0.45
     ಶ್ರೀ
    0.44
    0
    0.44
     وخ
    0.43
    za
    0.43
    POSITIVE LOGITS
    스는
    0.46
     digested
    0.45
    на
    0.42
    י
    0.42
     pronouncing
    0.42
    ي
    0.42
    و
    0.41
    لے
    0.41
     countable
    0.41
     angeles
    0.41
    Activations Density 0.004%

    No Known Activations