© 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. 39218
    Prev
    Next
    INDEX
    Explanations

    applications and OS platform

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

    . Returns, node, Belt

    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
     transcendence
    0.51
     enigma
    0.49
     inflex
    0.49
    ʣ
    0.48
     trocar
    0.47
    เสมอ
    0.47
    스키
    0.47
    %:
    0.47
     endearing
    0.46
     해요
    0.46
    POSITIVE LOGITS
     depleted
    0.49
    胚
    0.46
     м
    0.45
    unts
    0.45
    assert
    0.44
    ъ
    0.42
    नात
    0.41
    集中
    0.41
    sciences
    0.41
    <0xA6>
    0.40
    Activations Density 0.000%

    No Known Activations