© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 9865
    Prev
    Next
    INDEX
    Explanations

    safety and goal-oriented actions

    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
    ت
    1.20
    ون
    1.12
    סט
    1.11
    ம்
    1.08
    adeus
    1.07
    o
    1.04
    बाबा
    1.02
     دنوں
    1.02
    ン
    1.02
    𝙥
    1.01
    POSITIVE LOGITS
    }])
    1.50
     barring
    1.49
     perpetual
    1.44
     contestant
    1.43
     hoops
    1.40
    তে
    1.34
    勮
    1.33
    }))
    1.33
     scarcely
    1.32
     tulips
    1.32
    Activations Density 0.000%

    No Known Activations