© 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. 33386
    Prev
    Next
    INDEX
    Explanations

    characters and performances

    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
    ּוֹ
    -1.11
     they
    -1.06
     τῶν
    -1.00
    val
    -1.00
    tgt
    -0.99
    agon
    -0.94
     السياس
    -0.93
    Then
    -0.90
     około
    -0.90
     pObj
    -0.90
    POSITIVE LOGITS
     characters
    1.54
     character
    1.37
    characters
    1.31
    denk
    1.23
     personagem
    1.19
    karakter
    1.18
     karakter
    1.16
     personaje
    1.12
     Characters
    1.09
     traits
    1.04
    Activations Density 0.018%

    No Known Activations