© 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. 546
    Prev
    Next
    INDEX
    Explanations

    have access to

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

    possessions, experiences, states

    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
    ка
    0.40
     ，
    0.39
    𝟬
    0.38
    나
    0.35
    ك
    0.34
    ยาง
    0.32
    ০০
    0.32
    4
    0.32
     initializer
    0.32
    0
    0.32
    POSITIVE LOGITS
     been
    0.63
    ע
    0.55
    been
    0.49
     Been
    0.40
     BEEN
    0.39
    ри
    0.39
    Been
    0.38
     recourse
    0.37
    丝毫
    0.36
     trouble
    0.35
    Activations Density 0.769%

    No Known Activations