© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3000
    Prev
    Next
    INDEX
    Explanations

    numbers of games and words

    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_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
     decena
    0.89
    }=
    0.81
     habido
    0.81
    য়োজন
    0.80
    acheter
    0.80
    倍
    0.79
     personaje
    0.79
     倍
    0.79
    }+
    0.78
    phenyl
    0.75
    POSITIVE LOGITS
     supporters
    0.90
     possessions
    0.81
     defenses
    0.77
    goers
    0.75
     sprinkles
    0.74
     detractors
    0.72
     decorations
    0.70
     molecules
    0.70
     spoils
    0.69
     critics
    0.69
    Activations Density 0.182%

    No Known Activations