© 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. 110427
    Prev
    Next
    INDEX
    Explanations

    http and image references

    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
     there
    -1.04
    nterior
    -0.97
    восто
    -0.90
    يديا
    -0.86
    поги
    -0.86
     with
    -0.84
     had
    -0.84
    ậm
    -0.84
     túnel
    -0.83
     |]
    -0.82
    POSITIVE LOGITS
     app
    0.94
    ;<
    0.90
     пя
    0.89
    igth
    0.88
    insn
    0.86
     социальной
    0.86
     tp
    0.86
    aked
    0.84
     unn
    0.84
     sturdy
    0.83
    Activations Density 0.000%

    No Known Activations