© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25147
    Prev
    Next
    INDEX
    Explanations

    contributed, who, old, Send

    np_acts-logits-general · gemini-2.5-flash-lite

    specific items followed by details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ごとに
    0.50
     ओ
    0.50
     развития
    0.47
    細胞
    0.47
    続く
    0.47
    重ね
    0.46
    問題
    0.45
     डेवलपमेंट
    0.44
    複数の
    0.44
     неза
    0.44
    POSITIVE LOGITS
    ľad
    0.45
    imsu
    0.44
    Ḩ
    0.44
    ijdens
    0.43
     equipments
    0.41
    <0x95>
    0.41
     برخور
    0.41
    LevelLinking
    0.41
    나요
    0.40
    IFICATION
    0.40
    Activations Density 0.000%

    No Known Activations