© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15764
    Prev
    Next
    INDEX
    Explanations

    basic followed by a technical term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſen
    -2.81
    谖
    -2.53
     craz
    -2.53
    瓛
    -2.47
    鋇
    -2.47
    襌
    -2.44
     "
    -2.33
    idk
    -2.31
    厹
    -2.30
    大佬
    -2.25
    POSITIVE LOGITS
    Although
    3.39
    N
    3.38
    One
    3.31
    With
    3.30
    Even
    3.28
    While
    3.25
    Surprisingly
    3.25
    Despite
    3.17
    Though
    3.16
    During
    3.13
    Activations Density 0.014%

    No Known Activations