© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 1918
    Prev
    Next
    INDEX
    Explanations

    strong actions and intensity

    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_16_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
    𝓃
    0.44
     చిహ్
    0.43
    etheless
    0.41
     europeos
    0.40
    }$&$-
    0.40
     femelles
    0.38
    MSFont
    0.38
    𝘨
    0.38
     dólares
    0.38
    YU
    0.38
    POSITIVE LOGITS
     you
    0.43
     when
    0.41
     from
    0.38
     for
    0.37
     ;
    0.37
    /
    0.37
    </h3>
    0.36
    <h3>
    0.35
     with
    0.34
    当
    0.34
    Activations Density 0.140%

    No Known Activations