© 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. 212519
    Prev
    Next
    INDEX
    Explanations

    award, allowance, proposal

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

    greeting or break

    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
    vic
    0.52
    राम
    0.51
    Upload
    0.45
    reiro
    0.45
     Spaghetti
    0.44
    aves
    0.44
    νη
    0.43
    氻
    0.43
    बास
    0.43
    न
    0.42
    POSITIVE LOGITS
     proffered
    0.47
     proposent
    0.45
     proposer
    0.44
     >,
    0.44
     proposé
    0.44
     pondered
    0.44
     préf
    0.44
     pretende
    0.43
     proposing
    0.43
     brillant
    0.43
    Activations Density 0.000%

    No Known Activations