© 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. 34-GEMMASCOPE-RES-131K
    7. 117346
    Prev
    Next
    INDEX
    Explanations

    identical exact likeness

    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_34/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
     plutôt
    -0.96
    随之
    -0.92
     puedes
    -0.92
     errado
    -0.91
    NotImplemented
    -0.90
     verstehen
    -0.88
    NotEmpty
    -0.81
    ֪
    -0.79
     confianza
    -0.78
     tendremos
    -0.78
    POSITIVE LOGITS
     identical
    6.53
    identical
    5.28
     exactly
    4.75
    Iden
    4.31
     Iden
    4.31
    Exactly
    3.80
    exactly
    3.78
     identically
    3.75
     exact
    3.56
     exactamente
    3.36
    Activations Density 0.180%

    No Known Activations