© 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. 159171
    Prev
    Next
    INDEX
    Explanations

    occurrences and durations

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

    digital adoption

    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
     সাফল
    0.64
     distinguish
    0.52
    nosti
    0.51
    ハー
    0.51
    乀
    0.49
    㸳
    0.49
    年は
    0.49
    䤚
    0.49
    🏨
    0.49
     社会
    0.48
    POSITIVE LOGITS
     feitas
    0.46
    hi
    0.45
    owe
    0.45
    ;
    0.45
    )
    0.44
    ]
    0.44
    json
    0.44
     nah
    0.43
     ving
    0.43
    le
    0.43
    Activations Density 0.001%

    No Known Activations