© 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. 63901
    Prev
    Next
    INDEX
    Explanations

    SPDX-License-Identifier comments

    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
     VE
    -0.69
     menu
    -0.69
    artigen
    -0.67
    Tau
    -0.67
     Ref
    -0.67
     médecine
    -0.65
    вока
    -0.65
    menu
    -0.64
     Dit
    -0.64
    タカ
    -0.63
    POSITIVE LOGITS
    eters
    0.70
    jiang
    0.69
    <0x9B>
    0.69
     BigNumberish
    0.68
     Brittany
    0.68
     Espírito
    0.66
    PlainText
    0.65
    TOXIC
    0.63
    飛び
    0.63
     nitro
    0.63
    Activations Density 0.062%

    No Known Activations