© 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. 22-GEMMASCOPE-RES-131K
    7. 11423
    Prev
    Next
    INDEX
    Explanations

    making an effort to

    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_22/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
     with
    -1.95
    というわけで
    -1.85
    butuhkan
    -1.83
     these
    -1.81
     گوید
    -1.74
     matiz
    -1.63
    hadapi
    -1.60
    hasilkan
    -1.60
    しちゃ
    -1.58
    それにしても
    -1.58
    POSITIVE LOGITS
     to
    3.56
    j
    1.91
    y
    1.88
    he
    1.80
    “
    1.79
    we
    1.77
    ul
    1.76
     I
    1.75
    be
    1.74
    ens
    1.71
    Activations Density 0.030%

    No Known Activations