© 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. 37276
    Prev
    Next
    INDEX
    Explanations

    know us

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

    expressing frustration and powerlessness

    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
    纽约
    0.53
    纳
    0.47
    ማ
    0.44
    Visit
    0.44
    嚯
    0.43
    联邦
    0.43
    托
    0.43
    欢迎
    0.43
    这时候
    0.43
    ᐋ
    0.43
    POSITIVE LOGITS
     nyaman
    0.52
     petrol
    0.51
     mussten
    0.51
     tinham
    0.51
     rotting
    0.50
     disastrous
    0.49
     penelitian
    0.49
     AKS
    0.47
     UTI
    0.47
    kkal
    0.46
    Activations Density 0.000%

    No Known Activations