© 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. 78852
    Prev
    Next
    INDEX
    Explanations

    explain complex 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
     karenge
    0.51
    ма
    0.46
    ганда
    0.45
    ressing
    0.45
    ື
    0.44
    бу
    0.42
    прия
    0.42
    せずに
    0.42
     cứ
    0.42
    да
    0.42
    POSITIVE LOGITS
     Americas
    0.47
     namens
    0.46
     Schum
    0.46
     public
    0.46
    吣
    0.45
     جوړ
    0.44
    weil
    0.44
    नपुर
    0.44
     pouvoirs
    0.44
    深
    0.43
    Activations Density 0.001%

    No Known Activations