© 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. 248014
    Prev
    Next
    INDEX
    Explanations

    spines, human, cameras, stop

    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
     IUCN
    0.51
     uve
    0.49
     Indore
    0.45
     अन
    0.44
     '&
    0.44
    ума
    0.42
     Institut
    0.42
     ibis
    0.42
     cite
    0.42
     環境
    0.41
    POSITIVE LOGITS
    MOVEMENT
    0.47
    魇
    0.45
    Additional
    0.44
    additional
    0.43
    playback
    0.43
    Stop
    0.42
    بعد
    0.42
    Freight
    0.42
    Shader
    0.42
     Spal
    0.42
    Activations Density 0.001%

    No Known Activations