© 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. 118889
    Prev
    Next
    INDEX
    Explanations

    pp or PP followed by a letter or number

    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
     Stupid
    -1.02
    Izvori
    -0.81
     チ
    -0.79
     Convenience
    -0.79
     talking
    -0.78
    フライ
    -0.78
     existence
    -0.75
     silver
    -0.74
    存在
    -0.74
     privileged
    -0.73
    POSITIVE LOGITS
     PP
    1.07
    mascar
    0.83
    ául
    0.78
    仕上がり
    0.77
    delegate
    0.77
     Neri
    0.76
    ņš
    0.76
     userInput
    0.76
    ENDIX
    0.75
    仍在
    0.73
    Activations Density 0.032%

    No Known Activations