© 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. 34-GEMMASCOPE-RES-131K
    4. 118621
    Prev
    Next
    INDEX
    Explanations

    Warcraft, final, Poo after of

    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
    客户端
    -0.73
     wind
    -0.72
    cone
    -0.68
    ြ
    -0.66
     interference
    -0.65
    ient
    -0.65
     uncut
    -0.64
    Cone
    -0.63
     embryonic
    -0.63
     ս
    -0.63
    POSITIVE LOGITS
     Camus
    0.73
    اجة
    0.68
     carpeta
    0.66
    fundo
    0.66
    uose
    0.65
    CRA
    0.65
     मिल
    0.64
    ٥
    0.64
     mandiri
    0.64
    MDS
    0.63
    Activations Density 0.069%

    No Known Activations