© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9699
    Prev
    Next
    INDEX
    Explanations

    documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    denly
    1.40
    hotmail
    1.38
    mathfrak
    1.35
    за
    1.25
    트는
    1.25
    ्ट
    1.24
    pR
    1.22
    𝐞
    1.20
    prises
    1.19
    remia
    1.18
    POSITIVE LOGITS
     harassed
    1.59
     manuals
    1.47
    書き
    1.43
     literature
    1.42
     geschrieben
    1.38
     information
    1.37
     harassment
    1.37
     Catalogue
    1.36
     therein
    1.35
     brochures
    1.34
    Activations Density 0.236%

    No Known Activations