© 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. 202582
    Prev
    Next
    INDEX
    Explanations

    meals

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

    Link to

    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
     ascol
    0.47
    centric
    0.46
    colas
    0.45
    ogens
    0.45
    影
    0.45
    onske
    0.44
    شب
    0.44
    播
    0.44
    ون
    0.43
     peque
    0.43
    POSITIVE LOGITS
    ptr
    0.46
    Formation
    0.44
    Unique
    0.44
     protecting
    0.43
    forget
    0.43
    subsubsection
    0.41
    unique
    0.41
     በጣም
    0.41
    ];
    0.41
     mathrm
    0.41
    Activations Density 0.001%

    No Known Activations