© 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. 22-GEMMASCOPE-2-RES-262K
    7. 12797
    Prev
    Next
    INDEX
    Explanations

    tend to, tendency, tentative

    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_22_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
    ्मण
    1.00
    ɱ
    0.97
    ланд
    0.90
    튜
    0.89
    ೋ
    0.88
    精英
    0.87
    calc
    0.87
    ᆸ
    0.86
    ical
    0.86
     мене
    0.86
    POSITIVE LOGITS
    ulkar
    1.17
     Toward
    1.08
    encias
    1.07
    rils
    0.98
     toward
    0.90
     ioutil
    0.87
    ências
    0.86
    滪
    0.86
    entious
    0.86
     Towards
    0.85
    Activations Density 0.072%

    No Known Activations