© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65315
    Prev
    Next
    INDEX
    Explanations

    father dies

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

    characters with past struggles

    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_262k_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
     ultimately
    0.41
     Ultimately
    0.41
    徬
    0.41
    episode
    0.41
     konfl
    0.40
     결국
    0.39
     climax
    0.39
    ᅴ
    0.39
    ensão
    0.39
    當時
    0.38
    POSITIVE LOGITS
     disgraced
    0.44
    Congrats
    0.42
     years
    0.42
     सालाना
    0.42
     Congrats
    0.42
     Alexa
    0.41
     Waves
    0.40
     insurers
    0.40
     hasn
    0.39
     emailed
    0.39
    Activations Density 0.074%

    No Known Activations