© 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. 79951
    Prev
    Next
    INDEX
    Explanations

    architecture, setups, situation

    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
    ielleicht
    0.50
     Rechnung
    0.46
    කට
    0.45
    కోవడం
    0.45
    })(\
    0.44
    {(\
    0.44
    ikalische
    0.44
    阃
    0.44
    ländischen
    0.43
     상수
    0.43
    POSITIVE LOGITS
    p
    0.57
    1
    0.50
    3
    0.49
    4
    0.47
     for
    0.46
     due
    0.45
     didn
    0.44
     utiliz
    0.44
     isn
    0.44
    md
    0.44
    Activations Density 0.005%

    No Known Activations