© 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. 58398
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    explanation of computer commands like `cd`

    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
     germany
    0.45
    পাঁ
    0.43
     इसी
    0.43
     یہاں
    0.42
     scegli
    0.41
    아
    0.40
    April
    0.40
    wpi
    0.39
    praw
    0.39
    울
    0.39
    POSITIVE LOGITS
    众人
    0.40
    (\
    0.39
    াবিশ
    0.39
    (".");
    0.38
    branes
    0.37
    編成
    0.37
    ={\
    0.36
     теа
    0.35
    ？
    0.35
     kıs
    0.35
    Activations Density 0.000%

    No Known Activations