© 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. 29640
    Prev
    Next
    INDEX
    Explanations

    turn right, phase III, thence directions

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

    labels and evaluations

    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
     ৫৮
    0.48
    6
    0.46
     ৭৮
    0.44
    9
    0.44
    лот
    0.43
    充滿
    0.43
     ৮০
    0.43
     শত
    0.42
     ৬৫
    0.42
    5
    0.42
    POSITIVE LOGITS
     downlink
    0.37
     didSet
    0.36
     argu
    0.36
     inicial
    0.36
     iniziale
    0.35
     III
    0.35
     arrend
    0.35
    있다
    0.35
     electron
    0.34
    Ⅰ
    0.34
    Activations Density 0.033%

    No Known Activations