© 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. 209208
    Prev
    Next
    INDEX
    Explanations

    by emphasis

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

    descriptive context and interaction

    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
    jskiej
    0.51
    Novo
    0.50
    ित
    0.48
    SOD
    0.48
    쇼
    0.47
    ssf
    0.46
    zok
    0.46
    asakan
    0.46
    enzen
    0.45
    odan
    0.45
    POSITIVE LOGITS
     Capabilities
    0.49
     :
    0.47
    ధు
    0.46
     Cram
    0.45
     a
    0.45
     Teaching
    0.43
    嚇
    0.43
     crimson
    0.43
     Coverage
    0.43
     revisited
    0.43
    Activations Density 0.001%

    No Known Activations