© 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. 48987
    Prev
    Next
    INDEX
    Explanations

    Michele Davidson

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

    improved, advanced, reserved, or often followed by descriptors

    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
    erna
    0.53
    icen
    0.50
    ooo
    0.46
    unto
    0.45
    aire
    0.44
    ayo
    0.44
    atical
    0.43
    '
    0.43
    anın
    0.42
    ina
    0.42
    POSITIVE LOGITS
     injured
    0.48
     ἢ
    0.46
    傷
    0.45
     wounded
    0.45
    子は
    0.45
     exiled
    0.44
    ᱕
    0.44
    διά
    0.44
    コ
    0.44
     ロ
    0.44
    Activations Density 0.000%

    No Known Activations