© 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. 52235
    Prev
    Next
    INDEX
    Explanations

    inflatable, panorama, development, avoid, work together

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

    sus, echolocation, ears, whiskers, antennae

    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
     Soho
    0.48
     sahaja
    0.47
     and
    0.46
    \]
    0.45
     wyłącznie
    0.45
     Tubes
    0.44
     Inge
    0.44
     will
    0.43
    】,
    0.43
     Howard
    0.43
    POSITIVE LOGITS
    GEBURTS
    0.51
    ORICAL
    0.49
    快樂
    0.47
    歡
    0.47
    ncies
    0.46
    数目
    0.46
    ånd
    0.46
     قر
    0.46
    рії
    0.45
     ámbitos
    0.45
    Activations Density 0.000%

    No Known Activations