© 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. 240030
    Prev
    Next
    INDEX
    Explanations

    "required personal"

    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
     sparsim
    0.51
     arabe
    0.50
    𝚘
    0.49
     professe
    0.48
     /**@
    0.47
     unordered
    0.47
     확률
    0.47
     unsus
    0.46
     bò
    0.46
     lysis
    0.46
    POSITIVE LOGITS
    s
    0.57
    ،
    0.45
    PerTrial
    0.45
    ivant
    0.44
    ی
    0.43
    uk
    0.42
    ड्डा
    0.41
    ICK
    0.41
     তে
    0.41
     stolen
    0.41
    Activations Density 0.000%

    No Known Activations