© 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. 7708
    Prev
    Next
    INDEX
    Explanations

    reporting verbs like said or added

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

    said followed by punctuation

    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
     নেতৃত্বের
    0.35
     მნიშვნელ
    0.34
     heres
    0.32
    </h6>
    0.32
     இன்றைய
    0.31
     انجام
    0.30
    aar
    0.30
    führer
    0.29
     இன்று
    0.29
     अतीत
    0.29
    POSITIVE LOGITS
     biodegrad
    0.28
    ന്തു
    0.28
     للنساء
    0.28
     CORPER
    0.27
     biodegradation
    0.27
    Biod
    0.27
    ᅩ
    0.26
    Environment
    0.26
     cultivator
    0.26
     antivirus
    0.26
    Activations Density 0.046%

    No Known Activations