© 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. 28928
    Prev
    Next
    INDEX
    Explanations

    state of readiness or progress

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

    common phrases after words

    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
     käyttö
    0.44
     mnemonic
    0.43
     एमएन
    0.43
     skute
    0.43
    ට්
    0.43
     ruke
    0.42
    锶
    0.42
     počíta
    0.42
     pravil
    0.42
    ikopter
    0.42
    POSITIVE LOGITS
     Jess
    0.44
     बतौर
    0.43
     J
    0.43
     G
    0.42
     Francisco
    0.41
     Grav
    0.40
    Jess
    0.40
     Ross
    0.40
    phyl
    0.39
    anggap
    0.39
    Activations Density 0.000%

    No Known Activations