© 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. 174929
    Prev
    Next
    INDEX
    Explanations

    commercial terms about online services

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

    trends, historically, seasonings, unique

    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
     lessening
    0.54
     tokamaks
    0.52
     pundits
    0.51
     तीनों
    0.51
     ث
    0.50
     मानकों
    0.50
     নিউইয়
    0.50
     thermometers
    0.50
     जनक
    0.50
     WordPerfect
    0.50
    POSITIVE LOGITS
    р
    0.50
    concatenate
    0.48
    comments
    0.44
    탕
    0.44
    is
    0.43
    hire
    0.43
    circuit
    0.43
    genre
    0.43
    divide
    0.43
    doc
    0.42
    Activations Density 0.000%

    No Known Activations