© 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. 190132
    Prev
    Next
    INDEX
    Explanations

    responsible for, soon to

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

    professional and social platforms

    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
    ，
    0.51
     الحال
    0.44
    1
    0.43
    Marie
    0.43
    あって
    0.43
     Papa
    0.42
    <0x0D>
    0.41
     --
    0.41
    }
    0.41
    ،
    0.41
    POSITIVE LOGITS
    𝒎
    0.52
    𝒔
    0.50
    ड्यूल
    0.49
    ிகளில்
    0.48
     διαφορε
    0.47
     வடிவமை
    0.47
    గం
    0.46
    ссив
    0.46
    拶
    0.46
    ᴍ
    0.46
    Activations Density 0.000%

    No Known Activations