© 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. 10442
    Prev
    Next
    INDEX
    Explanations

    puntuations and diverse words

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

    blockage and difficulty breathing

    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
    Wheat
    0.42
    ानुसार
    0.42
    Ꮲ
    0.42
    So
    0.41
     गेहूं
    0.41
    ፩
    0.41
    이라고
    0.40
     Blunt
    0.40
    ያ
    0.40
    INESS
    0.40
    POSITIVE LOGITS
    GALAD
    0.51
    kbeta
    0.51
     strangled
    0.48
     осигурање
    0.47
    нер
    0.47
    恺
    0.47
    s
    0.46
     घेणे
    0.46
     מת
    0.44
     gấp
    0.44
    Activations Density 0.000%

    No Known Activations