© 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. 20900
    Prev
    Next
    INDEX
    Explanations

    titles and places

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

    specific factual statements

    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
    ╽
    0.35
    ╿
    0.34
     אשר
    0.33
    нку
    0.33
    ⁢</
    0.32
    ъ
    0.32
    쾨
    0.32
    ני
    0.32
    рифмети
    0.32
    calup
    0.32
    POSITIVE LOGITS
     N
    0.35
     T
    0.33
     R
    0.33
    7
    0.33
     K
    0.33
    9
    0.32
    5
    0.32
     E
    0.31
     July
    0.31
     B
    0.30
    Activations Density 0.290%

    No Known Activations