© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35082
    Prev
    Next
    INDEX
    Explanations

    another to other

    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
     Schluß
    -1.10
    ぶつ
    -1.09
    ofollow
    -1.09
    きち
    -1.06
    worldwide
    -1.05
     devoirs
    -1.03
    glBind
    -1.02
    敺
    -1.02
     exceptionally
    -1.01
    だけでは
    -1.01
    POSITIVE LOGITS
     or
    1.31
     with
    1.13
     Creating
    1.03
     without
    1.03
     HUGE
    1.00
    ～～
    0.98
     using
    0.97
     can
    0.95
     Having
    0.95
     predominant
    0.94
    Activations Density 0.045%

    No Known Activations