© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 53891
    Prev
    Next
    INDEX
    Explanations

    talk shows and talk radio

    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
    ControllerAdvice
    -0.80
    岐
    -0.74
    に
    -0.73
    angelog
    -0.73
    izzera
    -0.71
    </h1>
    -0.71
    ventude
    -0.69
    从来没有
    -0.69
    tahui
    -0.69
    ча
    -0.69
    POSITIVE LOGITS
    ative
    1.95
    ativeness
    1.77
     Talk
    1.26
    talk
    1.25
     about
    1.23
    Talk
    1.20
    atively
    1.19
    atives
    1.17
     talk
    1.06
    ATIVE
    1.03
    Activations Density 0.010%

    No Known Activations