© 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. 16071
    Prev
    Next
    INDEX
    Explanations

    questions starting with how

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

    how many, long, why, what

    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
     ekki
    0.47
     ikke
    0.44
    然而
    0.40
    >().
    0.39
     nebude
    0.39
    မဲ့
    0.38
    手的
    0.38
    ியின்
    0.38
    ержа
    0.38
    '].
    0.37
    POSITIVE LOGITS
     is
    0.77
     did
    0.74
     does
    0.72
     are
    0.66
     do
    0.66
     would
    0.62
    did
    0.62
    ?
    0.59
    soever
    0.58
    are
    0.53
    Activations Density 0.052%

    No Known Activations