© 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. 57141
    Prev
    Next
    INDEX
    Explanations

    about which

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

    birinci (first)

    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
    にする
    0.44
    tDBOutput
    0.44
    ま
    0.43
    瘦
    0.43
    冢
    0.42
     لنا
    0.42
    店内
    0.42
    日に
    0.42
    synthetic
    0.42
    olm
    0.42
    POSITIVE LOGITS
    একজন
    0.55
     conversaciones
    0.53
     seorang
    0.52
    -
    0.52
     evidences
    0.50
     birinci
    0.50
     Dark
    0.49
     interact
    0.48
     Light
    0.48
     disso
    0.48
    Activations Density 0.000%

    No Known Activations