© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6723
    Prev
    Next
    INDEX
    Explanations

    helpful and harmless

    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_17_width_16k_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
    қ
    0.90
    sequently
    0.88
    ifies
    0.84
     auxiliary
    0.83
    ient
    0.83
    ified
    0.82
    iously
    0.81
    ingly
    0.81
    స
    0.81
    uts
    0.80
    POSITIVE LOGITS
    危险
    1.26
     યોગ્ય
    1.20
     harmful
    1.18
     неприят
    1.16
    psilon
    1.16
     लाभदायक
    1.15
     ቀላል
    1.15
    꽤
    1.12
     agradable
    1.11
     приятно
    1.10
    Activations Density 0.601%

    No Known Activations