© 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. 57179
    Prev
    Next
    INDEX
    Explanations

    virtual machine

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

    common types

    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
    пол
    0.48
    afon
    0.45
    .’
    0.43
     monotonically
    0.43
    s
    0.42
    번호
    0.42
    avanja
    0.42
    ۔
    0.42
    peuta
    0.42
    Bike
    0.41
    POSITIVE LOGITS
     dietro
    0.51
     eril
    0.46
     خل
    0.44
     tenha
    0.43
     bakteri
    0.43
     abbia
    0.42
    alaman
    0.42
     Behind
    0.41
     skul
    0.41
     cameos
    0.41
    Activations Density 0.000%

    No Known Activations