© 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. 165891
    Prev
    Next
    INDEX
    Explanations

    food and drink

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

    conclusion or resolution

    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
     degrade
    0.57
    蛜
    0.53
     নদী
    0.50
     rhod
    0.50
     riparian
    0.50
    ană
    0.49
    ారె
    0.49
     赤
    0.49
    öre
    0.49
     ورود
    0.49
    POSITIVE LOGITS
    Clin
    0.46
     Pleas
    0.46
    Causes
    0.43
     examiners
    0.42
    Personally
    0.42
    Ис
    0.42
    Issue
    0.41
    YLE
    0.40
    <?
    0.39
    щении
    0.39
    Activations Density 0.001%

    No Known Activations