© 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. 72187
    Prev
    Next
    INDEX
    Explanations

    Needless to say

    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
     Why
    -1.23
     Here
    -1.18
     Actually
    -1.07
     its
    -1.07
     Remember
    -1.03
     Always
    -1.01
     Overall
    -1.00
     Listen
    -0.98
     }-
    -0.97
     What
    -0.94
    POSITIVE LOGITS
    ఱ
    1.27
     shat
    1.13
    ఙ
    1.09
    ⸫
    1.08
     zoude
    1.06
     intende
    1.05
    بدون
    1.04
     regionales
    1.02
     been
    1.02
    very
    1.00
    Activations Density 0.015%

    No Known Activations