© 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. 216697
    Prev
    Next
    INDEX
    Explanations

    join or upgrade your membership

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

    Russian translations

    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
    anlagen
    0.51
    হেল
    0.51
    frist
    0.50
    бри
    0.49
    徜
    0.49
    䇞
    0.49
    ভে
    0.48
    мовір
    0.48
    रिक्
    0.48
    𝟘
    0.47
    POSITIVE LOGITS
     took
    0.48
     concern
    0.43
     spirit
    0.43
     as
    0.42
     scores
    0.42
     psyche
    0.42
     sales
    0.41
    took
    0.40
     Torres
    0.40
     Soviet
    0.40
    Activations Density 0.000%

    No Known Activations