© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118616
    Prev
    Next
    INDEX
    Explanations

    raw video and audio formats

    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
     Bargain
    -0.69
    spb
    -0.67
    ό
    -0.66
    zte
    -0.65
     Statisti
    -0.65
     bargain
    -0.64
    ār
    -0.64
    PRET
    -0.64
     edizione
    -0.63
    bp
    -0.63
    POSITIVE LOGITS
     un
    1.59
     Raw
    1.10
     raw
    1.09
     Loss
    1.08
     RAW
    1.02
     loss
    0.98
     Un
    0.98
    RAW
    0.96
    Un
    0.93
    Raw
    0.89
    Activations Density 0.047%

    No Known Activations