© 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. 110443
    Prev
    Next
    INDEX
    Explanations

    Dear Sir:, Keywords:, following

    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
    ]),
    
    -0.96
    !',
    -0.94
    charpe
    -0.88
    >(&
    -0.87
    “)
    -0.82
    prising
    -0.81
     próprios
    -0.80
    sivité
    -0.79
    !”,
    -0.78
    ğinde
    -0.78
    POSITIVE LOGITS
    :-
    2.41
    :
    2.30
    :.
    1.95
    :",
    1.91
     :-
    1.90
    :]
    1.81
    :</
    1.78
    :—
    1.73
    :");
    1.73
    :
    
    1.69
    Activations Density 0.156%

    No Known Activations