© 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. 14191
    Prev
    Next
    INDEX
    Explanations

    actions and continuations

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

    actions and their direction

    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
     인한
    0.63
    ३
    0.58
     reconnaître
    0.56
     reprendre
    0.55
     récupérer
    0.54
     looming
    0.53
    ৩
    0.53
     devoured
    0.52
     mehreren
    0.52
     niềm
    0.52
    POSITIVE LOGITS
    g
    0.54
    redient
    0.50
    -
    0.48
    fes
    0.46
    prett
    0.45
    ალი
    0.44
    hass
    0.43
    toast
    0.43
    lang
    0.43
    تون
    0.43
    Activations Density 0.175%

    No Known Activations