© 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. 203670
    Prev
    Next
    INDEX
    Explanations

    entirely fabricated, fictional, or textual

    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
    </td>
    0.52
    1
    0.43
     cad
    0.42
     aspirated
    0.42
    শ
    0.42
     RUS
    0.41
     UR
    0.40
     RS
    0.39
     RU
    0.39
    <b>
    0.38
    POSITIVE LOGITS
    ofer
    0.55
     totiž
    0.54
    દાવાદ
    0.52
    ClearedBy
    0.51
    mert
    0.49
     machte
    0.49
    ujudkan
    0.49
     Ocak
    0.49
    pik
    0.49
    汅
    0.47
    Activations Density 0.005%

    No Known Activations