© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8955
    Prev
    Next
    INDEX
    Explanations

    blind and bound

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

    blindness

    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_40_width_16k_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
    auten
    0.46
     普通
    0.43
     angesch
    0.40
    戊
    0.40
    舉
    0.39
    䍜
    0.39
     grazie
    0.38
    ción
    0.37
    ’)
    0.37
    čení
    0.37
    POSITIVE LOGITS
     blind
    1.92
     Blind
    1.82
    Blind
    1.82
    blind
    1.78
    盲
    1.55
     blindness
    1.41
     blinded
    1.33
     ब्लाइंड
    1.28
     blinds
    1.24
     Bind
    1.21
    Activations Density 0.107%

    No Known Activations