© 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. 131712
    Prev
    Next
    INDEX
    Explanations

    measurements followed by related nouns

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

    participation, city, cultural, energy

    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
    োপাধ্যায়
    0.50
    रुण
    0.46
    decimals
    0.45
    Throws
    0.45
    িন্ত
    0.44
    有利
    0.44
     returnPacket
    0.43
    痨
    0.43
    MovementControls
    0.42
    裴
    0.42
    POSITIVE LOGITS
    :
    0.59
     participar
    0.52
     ener
    0.51
     participa
    0.51
     తొలి
    0.51
     (!)
    0.50
     cultural
    0.49
     observance
    0.49
     city
    0.49
     ceremon
    0.48
    Activations Density 0.000%

    No Known Activations