© 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. 110572
    Prev
    Next
    INDEX
    Explanations

    email body, communication, data, Q:

    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
    tifiable
    -0.84
    приклад
    -0.81
     during
    -0.81
    рез
    -0.77
     countless
    -0.75
    ६
    -0.73
     commonly
    -0.73
     because
    -0.73
    ductos
    -0.73
     from
    -0.72
    POSITIVE LOGITS
    Continu
    0.86
    began
    0.85
     }}
    0.85
    Umw
    0.85
    Procedimento
    0.84
    口感
    0.84
     tenuta
    0.84
    Indien
    0.84
    waves
    0.83
    

    0.83
    Activations Density 0.000%

    No Known Activations