© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166142
    Prev
    Next
    INDEX
    Explanations

    greetings with there

    np_acts-logits-general · gemini-2.5-flash-lite

    significant impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Because
    0.43
    ")],
    0.42
     I
    0.41
    usun
    0.40
     permanent
    0.40
     correctional
    0.39
     Seventh
    0.39
     widely
    0.38
    topics
    0.38
     развитию
    0.38
    POSITIVE LOGITS
     téléphon
    0.57
     thrott
    0.48
    嗓
    0.47
     Fleurit
    0.47
     entraîne
    0.46
    涡
    0.46
     étamines
    0.45
     succès
    0.45
    𝘫
    0.45
     throttle
    0.44
    Activations Density 0.000%

    No Known Activations