© 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. 116391
    Prev
    Next
    INDEX
    Explanations

    compensation for legal cases

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

    help and resources

    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
    veloped
    0.48
     phenotypic
    0.48
     partial
    0.48
     ця
    0.47
     بە
    0.47
     ἡ
    0.46
     都
    0.46
     substantial
    0.46
    )));
    0.45
     centralized
    0.45
    POSITIVE LOGITS
    Need
    0.51
    Choices
    0.46
    Ideas
    0.45
    Aplic
    0.44
    Ingredients
    0.44
     destrucción
    0.43
     Agregar
    0.42
    Crime
    0.42
    Casual
    0.42
    Ignore
    0.42
    Activations Density 0.001%

    No Known Activations