© 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
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 34942
    Prev
    Next
    INDEX
    Explanations

    organizations and personhood

    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_53_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
     pounds
    0.41
    ∞</
    0.41
    esha
    0.40
    팍
    0.39
    autista
    0.38
    pounds
    0.38
    Heaven
    0.37
     симпто
    0.37
     Antioxid
    0.37
     multit
    0.37
    POSITIVE LOGITS
    銓
    0.38
    BELL
    0.37
     Dodson
    0.37
     tiempo
    0.36
     փ
    0.36
     Disse
    0.36
     ph
    0.36
    プロセス
    0.36
    钏
    0.36
     disse
    0.35
    Activations Density 0.000%

    No Known Activations