© 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. 136940
    Prev
    Next
    INDEX
    Explanations

    descriptions of things and concepts

    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
    D
    0.62
    N
    0.53
    s
    0.48
    H
    0.47
    Dl
    0.45
    फ
    0.44
    ために
    0.44
    ]_
    0.44
    DH
    0.44
    B
    0.44
    POSITIVE LOGITS
     demie
    0.47
    ется
    0.47
    otive
    0.47
    ISHING
    0.44
    unregister
    0.44
    <unused718>
    0.44
     verkauft
    0.43
     электри
    0.43
     crian
    0.43
    arin
    0.43
    Activations Density 0.002%

    No Known Activations