© 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. 51896
    Prev
    Next
    INDEX
    Explanations

    the post

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

    asking for input again

    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
     stupe
    0.49
    ba
    0.47
     repress
    0.47
    Α
    0.46
    В
    0.46
    _
    0.43
     d
    0.43
    υ
    0.43
    פ
    0.43
     nga
    0.42
    POSITIVE LOGITS
     чтобы
    0.44
     インテリア
    0.43
     Imperio
    0.42
    လိုအပ်
    0.41
     финанси
    0.41
     önem
    0.40
     অফিসের
    0.40
     consenso
    0.40
     quedaría
    0.39
     سؤال
    0.39
    Activations Density 0.000%

    No Known Activations