© 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. 184880
    Prev
    Next
    INDEX
    Explanations

    expressing or asserting viewpoints

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

    how and why

    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
     ganglion
    0.44
    teg
    0.42
    penguin
    0.42
    BeginInit
    0.41
     layi
    0.41
     unen
    0.41
    mannschaft
    0.40
    淼
    0.40
     Samoa
    0.40
    ivil
    0.40
    POSITIVE LOGITS
    żyć
    0.46
    P
    0.45
    }+
    0.45
    看不到
    0.44
     ㄴ
    0.44
    V
    0.44
    =\
    0.43
    ్యాన్ని
    0.43
     ი
    0.43
    ：
    0.43
    Activations Density 0.000%

    No Known Activations