© 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. 22354
    Prev
    Next
    INDEX
    Explanations

    and performs

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

    gravity and g

    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
    il
    0.53
    8
    0.47
     Uncomment
    0.44
     Joaquim
    0.44
    7
    0.43
     ત્યાર
    0.43
     Shipment
    0.43
    zum
    0.42
     Ramb
    0.42
     पूछे
    0.41
    POSITIVE LOGITS
    겨
    0.47
     loudspeaker
    0.44
    IDAE
    0.43
     plaster
    0.40
    ittää
    0.40
     datth
    0.40
     formant
    0.40
    ENG
    0.40
     diathermy
    0.40
    ยาน
    0.39
    Activations Density 0.000%

    No Known Activations