© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 23007
    Prev
    Next
    INDEX
    Explanations

    to the destination

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

    maintaining state or progress

    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
     classroom
    0.46
    점
    0.43
    名は
    0.42
    銘
    0.41
    classroom
    0.40
    arton
    0.40
    수는
    0.40
    艶
    0.40
     aggravation
    0.39
     слово
    0.39
    POSITIVE LOGITS
    保持
    0.44
    isesti
    0.42
    ζο
    0.40
     maintain
    0.38
     ngừng
    0.37
     prosegu
    0.36
     jusque
    0.35
     hasta
    0.35
    wach
    0.35
     establish
    0.34
    Activations Density 0.000%

    No Known Activations