© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13733
    Prev
    Next
    INDEX
    Explanations

    `alien -i` to install

    np_acts-logits-general · gemini-2.5-flash-lite

    login with context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PRESSED
    0.46
    로서
    0.44
    ОВА
    0.43
    িসি
    0.42
    LETIN
    0.42
    齬
    0.42
    ER
    0.41
    記載
    0.41
    AZIONE
    0.41
    INUS
    0.41
    POSITIVE LOGITS
     thème
    0.52
     ethically
    0.49
     reconnection
    0.46
     mountains
    0.43
     goTo
    0.42
     estómago
    0.42
     chose
    0.41
     jetty
    0.41
     canopy
    0.41
     brandy
    0.41
    Activations Density 0.029%

    No Known Activations