© 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. 211207
    Prev
    Next
    INDEX
    Explanations

    concerning planning

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

    runtime, the, From, *, all,

    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
    𝘭
    0.48
    ಿಲ್ಲ
    0.46
     egalitarian
    0.44
    ENV
    0.44
    ेंस
    0.43
    arto
    0.43
    unified
    0.43
     invariable
    0.42
    sequential
    0.42
    뀐
    0.42
    POSITIVE LOGITS
    ۔
    0.58
     ۔
    0.47
     және
    0.44
     এবং
    0.44
    ным
    0.44
    对此
    0.44
     ذریع
    0.43
     naše
    0.43
     unserer
    0.43
     übers
    0.43
    Activations Density 0.000%

    No Known Activations