© 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. 33071
    Prev
    Next
    INDEX
    Explanations

    a favorite jumper people

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

    cause and effect

    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
     genial
    0.44
    ግ
    0.42
     acoustics
    0.41
     padrões
    0.41
    égard
    0.39
     undec
    0.38
    Preprocessing
    0.38
     honours
    0.38
     statistics
    0.38
    ileges
    0.37
    POSITIVE LOGITS
    導致
    0.49
    导致
    0.46
     মাসে
    0.46
    改變
    0.44
    弦
    0.44
    ొప్పి
    0.44
     ঘৃ
    0.43
     thác
    0.43
     देण्यासाठी
    0.43
    ောင်း
    0.42
    Activations Density 0.000%

    No Known Activations