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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12153
    Prev
    Next
    INDEX
    Explanations

    base button config

    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
     its
    -1.09
     two
    -0.98
    madonna
    -0.91
     and
    -0.90
    bermuda
    -0.88
    ઃ
    -0.86
    bumptech
    -0.83
     including
    -0.81
     Uniwers
    -0.81
     Nowy
    -0.80
    POSITIVE LOGITS
    ныя
    1.06
    gemeinden
    1.04
    viez
    1.02
     schoon
    1.01
     Kuch
    0.96
    禟
    0.96
    私の
    0.93
    LEZ
    0.93
    igerung
    0.92
     fré
    0.91
    Activations Density 0.080%

    No Known Activations