© 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. 115482
    Prev
    Next
    INDEX
    Explanations

    time and avoidance

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

    negative emotional states

    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
     direcciones
    0.47
     trabal
    0.44
     telefono
    0.43
    𝘿
    0.42
    MLElement
    0.42
     pecahan
    0.41
     znajdują
    0.40
    evice
    0.40
    󠁬
    0.40
     телефо
    0.39
    POSITIVE LOGITS
    학교
    0.48
     Consumption
    0.47
     Brake
    0.45
     Time
    0.43
     Sewage
    0.43
     TIME
    0.42
     Resin
    0.42
    时间的
    0.42
     Output
    0.41
     Brak
    0.41
    Activations Density 0.000%

    No Known Activations