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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33165
    Prev
    Next
    INDEX
    Explanations

    inner voice intuition guidance

    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
    سمبر
    -0.92
     explica
    -0.82
     рассказала
    -0.82
    Sharing
    -0.81
     fix
    -0.80
    culable
    -0.79
    lysm
    -0.78
    دهی
    -0.78
     blest
    -0.78
     Pius
    -0.78
    POSITIVE LOGITS
     voices
    2.83
     voice
    2.73
    voices
    2.05
     Voice
    1.96
    voice
    1.91
     voix
    1.91
    Voice
    1.87
    の声
    1.81
     Voices
    1.81
     whisper
    1.78
    Activations Density 0.025%

    No Known Activations