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. 7618
    Prev
    Next
    INDEX
    Explanations

    f. or F suivi de / ou

    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
     hí
    -0.81
    éenne
    -0.81
     aconse
    -0.80
     zawier
    -0.80
    削
    -0.79
    手が
    -0.77
     profundas
    -0.77
     rattle
    -0.75
     cas
    -0.75
     llegando
    -0.74
    POSITIVE LOGITS
     FZ
    1.02
     Fx
    1.00
     Ff
    0.94
     FR
    0.94
     FRAN
    0.91
     F
    0.89
     Fm
    0.89
    ׁ
    0.88
     FOTO
    0.88
     FEN
    0.87
    Activations Density 2.184%

    No Known Activations