© 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. 20624
    Prev
    Next
    INDEX
    Explanations

    felt covers, very liberal

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

    disks, chuck, beef, selves, solve

    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
    tiktok
    0.56
    p
    0.53
    in
    0.52
    There
    0.51
    n
    0.50
    NP
    0.50
    i
    0.50
    Head
    0.50
    Hor
    0.49
    use
    0.48
    POSITIVE LOGITS
     hati
    0.52
     hijau
    0.52
    쥬
    0.49
     Василий
    0.49
     நீர்
    0.49
     río
    0.49
     كلمه
    0.48
     Aguas
    0.48
     convenio
    0.48
     clockRadius
    0.48
    Activations Density 0.000%

    No Known Activations