© 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. 223347
    Prev
    Next
    INDEX
    Explanations

    official Lomography

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

    verification and employee interests

    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
    "-
    0.51
    ".
    0.47
     Statistics
    0.44
    "\
    0.44
    "--
    0.44
    ീകരണ
    0.44
     outwardly
    0.43
     Victorian
    0.43
    "
    0.43
    olidated
    0.43
    POSITIVE LOGITS
     flashbacks
    0.49
    दिनी
    0.47
    デイ
    0.46
    PosY
    0.46
    יום
    0.46
     replying
    0.46
     uploads
    0.44
     depots
    0.44
     sighs
    0.44
    ッカ
    0.43
    Activations Density 0.001%

    No Known Activations