© 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. 4434
    Prev
    Next
    INDEX
    Explanations

    the followed by superlatives

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

    breakdown of why, how, or facts

    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
     कुनै
    0.34
     आफ्नो
    0.34
    ָד
    0.33
    Კ
    0.32
    📐
    0.30
     bottomRight
    0.30
     terminates
    0.29
     initialise
    0.29
    VIDED
    0.29
     TestAvg
    0.29
    POSITIVE LOGITS
    we
    0.35
    -
    0.34
    amb
    0.33
    %
    0.33
    yn
    0.32
    í
    0.32
    3
    0.32
    с
    0.31
    ag
    0.31
    ak
    0.31
    Activations Density 0.280%

    No Known Activations