© 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. 125473
    Prev
    Next
    INDEX
    Explanations

    deployment and related actions

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

    development and installation

    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
     R
    0.68
     DR
    0.55
    RIC
    0.55
    <start_of_image>
    0.55
    r
    0.53
    z
    0.51
     P
    0.50
     Y
    0.49
     RAY
    0.48
    j
    0.47
    POSITIVE LOGITS
    කිය
    0.52
     tiem
    0.52
    ᇂ
    0.50
    ቀት
    0.50
     explicado
    0.50
    சொ
    0.49
     explique
    0.49
     elementName
    0.49
     முடியாது
    0.47
    サラダ
    0.47
    Activations Density 0.000%

    No Known Activations