© 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. 21403
    Prev
    Next
    INDEX
    Explanations

    on the season

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

    on followed by dates or events

    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
    大臣
    0.40
     বলি
    0.37
    propto
    0.37
    ブロック
    0.37
     earum
    0.37
    ┃
    0.36
    <0xDF>
    0.36
    venuto
    0.36
    ∝
    0.36
    ⿲
    0.36
    POSITIVE LOGITS
    Rush
    0.43
     整
    0.42
     الوطنية
    0.42
    Abb
    0.41
     उछ
    0.41
     defensively
    0.40
    Meta
    0.39
     Meta
    0.39
    igamma
    0.39
    چھ
    0.38
    Activations Density 0.031%

    No Known Activations