© 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. 48689
    Prev
    Next
    INDEX
    Explanations

    last name components

    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
    hampton
    -1.02
    lusst
    -1.02
    申し上げます
    -0.95
     magaz
    -0.94
    alist
    -0.94
    言葉を
    -0.87
     apartament
    -0.86
     Appetit
    -0.85
    ﾅ
    -0.84
    诙
    -0.84
    POSITIVE LOGITS
     médec
    1.10
     probiotics
    1.02
    也会
    1.01
    materialien
    1.01
     \%$,
    0.97
     totes
    0.96
    Bibliograf
    0.96
     onderste
    0.95
    Meghan
    0.93
     festge
    0.93
    Activations Density 0.114%

    No Known Activations