© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82199
    Prev
    Next
    INDEX
    Explanations

    battery usage and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tenth
    0.58
    guessed
    0.54
     आवासीय
    0.47
    TaskPojo
    0.45
    प्री
    0.45
    breath
    0.45
    }');
    0.44
    luğu
    0.44
    ਸ
    0.44
     प्रतिनिध
    0.44
    POSITIVE LOGITS
    ffler
    0.43
     moles
    0.42
     ligation
    0.41
     genau
    0.41
    υσ
    0.40
     grabbing
    0.40
     cabbage
    0.40
     couplings
    0.39
    ifton
    0.39
     digging
    0.39
    Activations Density 0.000%

    No Known Activations