© 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. 109550
    Prev
    Next
    INDEX
    Explanations

    shift in direction

    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
     diatur
    -0.93
     heiligen
    -0.91
    عالی
    -0.86
    METHODOLOGY
    -0.85
     AssemblyCulture
    -0.84
     föl
    -0.84
    ্ড
    -0.84
     Glaubens
    -0.82
     haine
    -0.81
     lámina
    -0.81
    POSITIVE LOGITS
     away
    6.59
    Away
    4.41
     Away
    4.22
    away
    4.06
     AWAY
    3.97
    AWAY
    3.38
     towards
    2.69
     toward
    2.61
     to
    2.02
    eaway
    1.95
    Activations Density 0.067%

    No Known Activations