© 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. 77444
    Prev
    Next
    INDEX
    Explanations

    supercritical, pump, second, Lord, Judah

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

    personality, interests, company culture

    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
     émer
    0.46
     बृ
    0.45
     expériences
    0.43
     Automation
    0.43
     triage
    0.43
    Ao
    0.42
    &(
    0.42
    ارة
    0.42
     végétation
    0.41
     permanence
    0.40
    POSITIVE LOGITS
     illiterate
    0.55
    iosity
    0.52
     Акы
    0.47
    ർഡ്
    0.47
     !$
    0.46
    strcmp
    0.44
     तुझ
    0.44
     எதிர்பார
    0.44
     જી
    0.43
    ț
    0.43
    Activations Density 0.000%

    No Known Activations