© 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. 174559
    Prev
    Next
    INDEX
    Explanations

    The same others

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

    Management, sequences, outcomes

    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
    لو
    0.50
    缄
    0.47
    shaders
    0.45
    药品
    0.45
     网络
    0.44
    ktop
    0.44
    ignor
    0.44
    窃
    0.44
    解决
    0.43
    más
    0.43
    POSITIVE LOGITS
     może
    0.49
     pail
    0.47
     sleeve
    0.46
     audi
    0.46
     blister
    0.46
     Matic
    0.46
     varic
    0.46
     erscheint
    0.46
    量が
    0.45
     officielle
    0.44
    Activations Density 0.000%

    No Known Activations