© 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. 107096
    Prev
    Next
    INDEX
    Explanations

    intergenerational

    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
     जिन
    -0.71
     tropical
    -0.66
    industrie
    -0.66
    缤
    -0.65
    substring
    -0.65
     ')[
    -0.65
     BROTHER
    -0.64
     зимой
    -0.64
     rappeler
    -0.63
    stray
    -0.63
    POSITIVE LOGITS
     generational
    4.22
    generational
    3.92
     inter
    3.89
     generations
    3.20
    inter
    2.63
     generation
    2.52
     Generations
    2.48
     Inter
    2.44
    Inter
    2.41
    generation
    2.36
    Activations Density 0.039%

    No Known Activations