© 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. 31953
    Prev
    Next
    INDEX
    Explanations

    bread crumbs

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

    plus or optional

    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
    0.51
    bilir
    0.51
    Θ
    0.49
    OP
    0.48
    Ö
    0.47
    Ρ
    0.46
    Ο
    0.46
    R
    0.45
    RK
    0.44
    Io
    0.44
    POSITIVE LOGITS
     reim
    0.48
     obligatoire
    0.47
     dues
    0.47
     fleas
    0.46
     ch
    0.46
     employ
    0.46
     conseil
    0.45
     constitue
    0.45
     lounging
    0.45
     bras
    0.45
    Activations Density 0.000%

    No Known Activations