© 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. 150972
    Prev
    Next
    INDEX
    Explanations

    academic conferences

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

    issuing bank, brown words

    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
    Mol
    0.47
    S
    0.46
     Audio
    0.45
     Forst
    0.44
    病情
    0.44
     General
    0.43
    ুকু
    0.43
     Mol
    0.43
    拄
    0.42
    D
    0.42
    POSITIVE LOGITS
    д
    0.55
    வெ
    0.54
     आवेग
    0.50
    ától
    0.50
    ates
    0.49
     வைக்க
    0.47
    álló
    0.47
    ładow
    0.47
     실패
    0.46
    곳
    0.46
    Activations Density 0.001%

    No Known Activations