© 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. 110455
    Prev
    Next
    INDEX
    Explanations

    you will / you should

    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
    ceiver
    -0.79
     untreated
    -0.73
     wrist
    -0.72
     Tüm
    -0.71
     consuma
    -0.71
     v
    -0.70
    hamilton
    -0.70
    ktı
    -0.70
    Trie
    -0.70
     sehen
    -0.70
    POSITIVE LOGITS
     aureus
    0.82
     righe
    0.82
     Mandi
    0.77
     pié
    0.77
     Milner
    0.77
    ッポン
    0.77
    NOM
    0.76
    øde
    0.74
     Sono
    0.73
     citer
    0.73
    Activations Density 0.000%

    No Known Activations