Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7770
    Prev
    Next
    INDEX
    Explanations

    html input tag attributes

    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
     }),
    -0.90
    amilya
    -0.89
     esteve
    -0.89
     jopa
    -0.88
    KommentareTeilen
    -0.88
     {}),
    -0.82
    ℙ
    -0.82
    jekt
    -0.82
    },{
    -0.81
    }}>
    -0.81
    POSITIVE LOGITS
     class
    1.44
     required
    1.40
     needed
    1.09
    required
    1.03
     type
    1.01
    class
    0.94
     require
    0.89
     Required
    0.86
     types
    0.85
     name
    0.84
    Activations Density 0.003%

    No Known Activations