© 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. 52424
    Prev
    Next
    INDEX
    Explanations

    lovely lace, murderesses, tennis players

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

    word followed by punctuation/marker

    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
     Awesome
    0.57
     g
    0.57
     Ilya
    0.56
     il
    0.55
     m
    0.54
     Hooks
    0.52
     Il
    0.51
     stressed
    0.50
     Devil
    0.50
     flammable
    0.50
    POSITIVE LOGITS
    )।
    0.58
    ור
    0.53
    сіі
    0.50
    ].
    0.49
    قی
    0.49
    México
    0.49
    ).
    0.49
    τα
    0.49
    तां
    0.47
    ।)
    0.47
    Activations Density 0.001%

    No Known Activations