© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 14054
    Prev
    Next
    INDEX
    Explanations

    naming and describing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     బాధ
    0.45
    physiological
    0.45
    ymptoms
    0.41
     Reproduced
    0.40
    遽
    0.40
     அடிக்கடி
    0.40
    PERATURE
    0.39
    espec
    0.38
    ➔
    0.38
    脆弱
    0.38
    POSITIVE LOGITS
     aptly
    0.49
     nommé
    0.43
     hiko
    0.42
     beacons
    0.40
     sleek
    0.40
     ventures
    0.40
     dusk
    0.40
     Dusk
    0.40
     Dawn
    0.39
     R
    0.38
    Activations Density 0.172%

    No Known Activations