© 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. 216479
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

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

    gradual subtle but

    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
     }\
    0.56
    ન્
    0.53
     อยาก
    0.48
    ะ
    0.48
     शोध
    0.47
    LLOW
    0.47
    enquête
    0.47
     sarees
    0.46
    sorting
    0.46
    }}
    0.45
    POSITIVE LOGITS
     impressively
    0.46
     برا
    0.43
     sposob
    0.42
    azos
    0.42
    信号
    0.41
     plan
    0.41
    Источник
    0.40
    НУ
    0.40
     armband
    0.40
    联
    0.39
    Activations Density 0.000%

    No Known Activations