© 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. 121453
    Prev
    Next
    INDEX
    Explanations

    email password

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

    is in Stories Marsh

    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
    дован
    0.50
     вследствие
    0.49
    することにより
    0.48
     добре
    0.48
    рован
    0.47
    ⟹
    0.47
    pte
    0.45
    iqui
    0.45
    年至
    0.45
     サー
    0.44
    POSITIVE LOGITS
    이사
    0.45
    Gel
    0.44
    Issue
    0.44
     anest
    0.42
     ओलंपिक
    0.42
    ީ
    0.41
     Alic
    0.41
    ണിയ
    0.41
    Is
    0.40
    Description
    0.40
    Activations Density 0.000%

    No Known Activations