© 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. 169915
    Prev
    Next
    INDEX
    Explanations

    .", "call", "0871", "6", "7", "60"

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

    gland ( , White doesn , seconds . , putting ducks

    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
    詆
    0.57
    倛
    0.56
    守
    0.55
     रद्द
    0.52
     구독
    0.51
    瓦
    0.51
    𝘰
    0.51
    FinishLaunching
    0.51
    aseña
    0.50
     Entrenamiento
    0.50
    POSITIVE LOGITS
    ",
    0.55
    ".
    0.53
     pathways
    0.53
     ",
    0.53
     global
    0.52
     mapping
    0.51
     internation
    0.51
     ".
    0.50
     academies
    0.50
     "
    0.49
    Activations Density 0.001%

    No Known Activations