© 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. 146106
    Prev
    Next
    INDEX
    Explanations

    approved, supported, often

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

    words following 'say' or 'was'

    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
    lords
    0.46
     abusing
    0.44
    ™.
    0.44
    ghijklmnopqrst
    0.43
     platforms
    0.42
    ™,
    0.42
     chilling
    0.42
    generator
    0.41
     generator
    0.41
    ኞች
    0.41
    POSITIVE LOGITS
    驃
    0.51
     luminoso
    0.49
     recue
    0.49
     informacije
    0.49
    ጴ
    0.49
     dissected
    0.48
     permesso
    0.47
    ಸ್
    0.47
    پی
    0.47
    pyrrolo
    0.47
    Activations Density 0.000%

    No Known Activations