© 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. 105367
    Prev
    Next
    INDEX
    Explanations

    items for sale

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

    existence of

    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
    Otto
    0.46
    --------------
    0.44
     کوردستان
    0.44
    Legal
    0.44
    INGO
    0.44
    Atom
    0.43
    Pub
    0.42
    Arch
    0.42
    Helvetica
    0.42
    _+
    0.41
    POSITIVE LOGITS
     waving
    0.50
     vooraf
    0.48
     este
    0.47
     referring
    0.46
     evoking
    0.45
     relating
    0.44
     kicking
    0.44
     covariance
    0.44
     footsteps
    0.44
     approving
    0.44
    Activations Density 0.001%

    No Known Activations