© 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. 22-GEMMASCOPE-RES-131K
    7. 128506
    Prev
    Next
    INDEX
    Explanations

    my iPhone

    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_22/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
     también
    -1.41
     instagram
    -1.40
     our
    -1.40
     Instagram
    -1.30
     Pinterest
    -1.30
     tienen
    -1.25
     Reised
    -1.23
     també
    -1.21
     influencer
    -1.20
     เพราะ
    -1.20
    POSITIVE LOGITS
     you
    1.64
     chré
    1.27
     your
    1.27
     RECOVERY
    1.18
    offensive
    1.16
    讓你
    1.16
     Windows
    1.15
     선택
    1.14
     Eſ
    1.13
    viously
    1.12
    Activations Density 0.235%

    No Known Activations