© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117425
    Prev
    Next
    INDEX
    Explanations

    make voices heard

    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
     frecuente
    -0.85
     мозга
    -0.81
    mathscr
    -0.77
    Verweise
    -0.76
     QName
    -0.75
    vap
    -0.75
     criteria
    -0.75
     сообщил
    -0.75
     relationships
    -0.74
     Га
    -0.74
    POSITIVE LOGITS
     voice
    4.03
     voices
    3.84
    voice
    3.03
    voices
    2.98
     Voice
    2.72
    Voice
    2.72
     voic
    2.63
     VOICE
    2.61
    VOICE
    2.48
     voix
    2.42
    Activations Density 0.035%

    No Known Activations