© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104185
    Prev
    Next
    INDEX
    Explanations

    BTC, currency, GTA, IV, Barça, Football clubs, Netherlands Film

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }
    -2.97
    辚
    -2.58
    .
    -2.50
    蠃
    -2.25
    hassee
    -2.25
    ない
    -2.25
    歺
    -2.23
    ].
    -2.22
    地看着
    -2.20
    鉝
    -2.20
    POSITIVE LOGITS
    身边的
    2.44
     besonderen
    2.16
     leichten
    2.08
    毳
    2.06
     akhirnya
    2.00
     ewigen
    2.00
     magnético
    1.98
     glimpses
    1.97
     elástico
    1.95
    ፉ
    1.95
    Activations Density 0.001%

    No Known Activations